• Journal of the Korea Society for Simulation
• /
• v.30 no.1
• /
• pp.75-85
• /
• 2021

In this paper, we present a deep neural network-based prediction model that processes and analyzes the corporate credit and personal credit information of individual business owners as a new method to predict the default rate of individual business more accurately. In modeling research in various fields, feature selection techniques have been actively studied as a method for improving performance, especially in predictive models including many features. In this paper, after statistical verification of macroeconomic indicators (macro variables) and credit information (micro variables), which are input variables used in the default rate prediction model, additionally, through the credit information feature selection method, the final feature set that improves prediction performance was identified. The proposed credit information feature selection method as an iterative & hybrid method that combines the filter-based and wrapper-based method builds submodels, constructs subsets by extracting important variables of the maximum performance submodels, and determines the final feature set through prediction performance analysis of the subset and the subset combined set.

• KDI Journal of Economic Policy
• /
• v.32 no.4
• /
• pp.1-34
• /
• 2010

We conduct a comprehensive risk analysis of household debt in Korea for the first time using the whole sample credit bureau (CB) data of 2.2 million individual debtors. After analysing debt service capacity profiles of debtor groups classified by the borrower characteristics such as income, age, occupation, credit scoring, and the type of creditor business companies, we investigate the impact of interest rate and income changes on debt service-to-income ratios (DTIs) and default rates of respective debtor groups. Empirical results indicate that debt service burdens are relatively high for low income wage earners, high income self-employed, low income capital and card loan holders, and high income mutual savings loan holders. We also find that debtors from multiple financial companies are particularly weak in their debt service capacity. The scenario analysis indicates that financial companies, with the current level of capital buffers, may be able to absorb negative consequences arising from the increase in DTIs and loan default rates if the interest rate and income changes remain modest. However, the negative consequences may fall disproportionately on non-bank financial companies such as capital, credit card, and mutual savings banks, whose debtors' DTIs are already high. We also find that the refinancing risk of household debt is relatively high in Korea as more than half of household mortgage debts are bullet loans. As the DTIs of mortgage loan holders are already high, under the current DTI regulation, mortgage loans may not be readily refinanced especially when the interest rate rises. Disruptions in mortgage loan refinancing may put downward pressure on housing prices, which may in turn magnify refinancing risk under the current loan-to-value (LTV) regulation. Overall our analysis suggests that, for more effective monitoring of household debt risk, it is necessary to combine existing surveillance schemes based on macro aggregate indicators with more comprehensive and detailed risk analyses based on micro individual data.